Change implementation of MergedDocuments::iter_top_level_fields

crates/index-scheduler/src/batch.rs

@@ -29,6 +29,7 @@ use bumpalo::collections::CollectIn;
 use bumpalo::Bump;
 use dump::IndexMetadata;
 use meilisearch_types::batches::BatchId;
+use meilisearch_types::error::Code;
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader, PrimaryKey};
 use meilisearch_types::milli::heed::CompactionOption;
@@ -688,9 +689,7 @@ impl IndexScheduler {
                     let index = self.index_mapper.index(&rtxn, name)?;
                     let dst = temp_snapshot_dir.path().join("indexes").join(uuid.to_string());
                     fs::create_dir_all(&dst)?;
-                    index
-                        .copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)
-                        .map_err(|e| Error::from_milli(e, Some(name.to_string())))?;
+                    index.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
                 }
 
                 drop(rtxn);
@@ -792,19 +791,16 @@ impl IndexScheduler {
                             let content_file = self.file_store.get_update(content_file)?;
 
                             let reader = DocumentsBatchReader::from_reader(content_file)
-                                .map_err(|e| Error::from_milli(e.into(), None))?;
+                                .map_err(milli::Error::from)?;
 
                             let (mut cursor, documents_batch_index) =
                                 reader.into_cursor_and_fields_index();
 
-                            while let Some(doc) = cursor
-                                .next_document()
-                                .map_err(|e| Error::from_milli(e.into(), None))?
+                            while let Some(doc) =
+                                cursor.next_document().map_err(milli::Error::from)?
                             {
-                                dump_content_file.push_document(
-                                    &obkv_to_object(doc, &documents_batch_index)
-                                        .map_err(|e| Error::from_milli(e, None))?,
-                                )?;
+                                dump_content_file
+                                    .push_document(&obkv_to_object(doc, &documents_batch_index)?)?;
                             }
                             dump_content_file.flush()?;
                         }
@@ -818,41 +814,27 @@ impl IndexScheduler {
                     let metadata = IndexMetadata {
                         uid: uid.to_owned(),
                         primary_key: index.primary_key(&rtxn)?.map(String::from),
-                        created_at: index
-                            .created_at(&rtxn)
-                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?,
-                        updated_at: index
-                            .updated_at(&rtxn)
-                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?,
+                        created_at: index.created_at(&rtxn)?,
+                        updated_at: index.updated_at(&rtxn)?,
                     };
                     let mut index_dumper = dump.create_index(uid, &metadata)?;
 
                     let fields_ids_map = index.fields_ids_map(&rtxn)?;
                     let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
-                    let embedding_configs = index
-                        .embedding_configs(&rtxn)
-                        .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                    let embedding_configs = index.embedding_configs(&rtxn)?;
 
-                    let documents = index
-                        .all_documents(&rtxn)
-                        .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
                     // 3.1. Dump the documents
-                    for ret in documents {
+                    for ret in index.all_documents(&rtxn)? {
                         if self.must_stop_processing.get() {
                             return Err(Error::AbortedTask);
                         }
 
-                        let (id, doc) =
-                            ret.map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                        let (id, doc) = ret?;
 
-                        let mut document =
-                            milli::obkv_to_json(&all_fields, &fields_ids_map, doc)
-                                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                        let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)?;
 
                         'inject_vectors: {
-                            let embeddings = index
-                                .embeddings(&rtxn, id)
-                                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                            let embeddings = index.embeddings(&rtxn, id)?;
 
                             if embeddings.is_empty() {
                                 break 'inject_vectors;
@@ -863,7 +845,7 @@ impl IndexScheduler {
                                 .or_insert(serde_json::Value::Object(Default::default()));
 
                             let serde_json::Value::Object(vectors) = vectors else {
-                                let user_err = milli::Error::UserError(
+                                return Err(milli::Error::UserError(
                                     milli::UserError::InvalidVectorsMapType {
                                         document_id: {
                                             if let Ok(Some(Ok(index))) = index
@@ -877,9 +859,8 @@ impl IndexScheduler {
                                         },
                                         value: vectors.clone(),
                                     },
-                                );
-
-                                return Err(Error::from_milli(user_err, Some(uid.to_string())));
+                                )
+                                .into());
                             };
 
                             for (embedder_name, embeddings) in embeddings {
@@ -909,8 +890,7 @@ impl IndexScheduler {
                         index,
                         &rtxn,
                         meilisearch_types::settings::SecretPolicy::RevealSecrets,
-                    )
-                    .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                    )?;
                     index_dumper.settings(&settings)?;
                     Ok(())
                 })?;
@@ -966,8 +946,7 @@ impl IndexScheduler {
                 // the entire batch.
                 let res = || -> Result<()> {
                     let index_rtxn = index.read_txn()?;
-                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
-                        .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
                     let mut wtxn = self.env.write_txn()?;
                     self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
                     wtxn.commit()?;
@@ -1009,12 +988,10 @@ impl IndexScheduler {
                     );
                     builder.set_primary_key(primary_key);
                     let must_stop_processing = self.must_stop_processing.clone();
-                    builder
-                        .execute(
+                    builder.execute(
                         |indexing_step| tracing::debug!(update = ?indexing_step),
                         || must_stop_processing.get(),
-                        )
-                        .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))?;
+                    )?;
                     index_wtxn.commit()?;
                 }
 
@@ -1031,8 +1008,7 @@ impl IndexScheduler {
                 let res = || -> Result<()> {
                     let mut wtxn = self.env.write_txn()?;
                     let index_rtxn = index.read_txn()?;
-                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
-                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
+                    let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)?;
                     self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
                     wtxn.commit()?;
                     Ok(())
@@ -1055,9 +1031,7 @@ impl IndexScheduler {
                 let number_of_documents = || -> Result<u64> {
                     let index = self.index_mapper.index(&wtxn, &index_uid)?;
                     let index_rtxn = index.read_txn()?;
-                    index
-                        .number_of_documents(&index_rtxn)
-                        .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))
+                    Ok(index.number_of_documents(&index_rtxn)?)
                 }()
                 .unwrap_or_default();
 
@@ -1214,10 +1188,8 @@ impl IndexScheduler {
         };
 
         match operation {
-            IndexOperation::DocumentClear { index_uid, mut tasks } => {
-                let count = milli::update::ClearDocuments::new(index_wtxn, index)
-                    .execute()
-                    .map_err(|e| Error::from_milli(e, Some(index_uid)))?;
+            IndexOperation::DocumentClear { mut tasks, .. } => {
+                let count = milli::update::ClearDocuments::new(index_wtxn, index).execute()?;
 
                 let mut first_clear_found = false;
                 for task in &mut tasks {
@@ -1237,7 +1209,7 @@ impl IndexScheduler {
                 Ok(tasks)
             }
             IndexOperation::DocumentOperation {
-                index_uid,
+                index_uid: _,
                 primary_key,
                 method,
                 operations,
@@ -1263,17 +1235,13 @@ impl IndexScheduler {
 
                 let mut content_files_iter = content_files.iter();
                 let mut indexer = indexer::DocumentOperation::new(method);
-                let embedders = index
-                    .embedding_configs(index_wtxn)
-                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
-                let embedders = self.embedders(index_uid.clone(), embedders)?;
+                let embedders = index.embedding_configs(index_wtxn)?;
+                let embedders = self.embedders(embedders)?;
                 for operation in operations {
                     match operation {
                         DocumentOperation::Add(_content_uuid) => {
                             let mmap = content_files_iter.next().unwrap();
-                            indexer
-                                .add_documents(mmap)
-                                .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
+                            indexer.add_documents(mmap)?;
                         }
                         DocumentOperation::Delete(document_ids) => {
                             let document_ids: bumpalo::collections::vec::Vec<_> = document_ids
@@ -1298,8 +1266,7 @@ impl IndexScheduler {
                     }
                 };
 
-                let (document_changes, operation_stats, primary_key) = indexer
-                    .into_changes(
+                let (document_changes, operation_stats, primary_key) = indexer.into_changes(
                     &indexer_alloc,
                     index,
                     &rtxn,
@@ -1307,8 +1274,7 @@ impl IndexScheduler {
                     &mut new_fields_ids_map,
                     &|| must_stop_processing.get(),
                     &send_progress,
-                    )
-                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
+                )?;
 
                 let mut addition = 0;
                 for (stats, task) in operation_stats.into_iter().zip(&mut tasks) {
@@ -1355,15 +1321,14 @@ impl IndexScheduler {
                         embedders,
                         &|| must_stop_processing.get(),
                         &send_progress,
-                    )
-                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
+                    )?;
 
                     tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
 
                 Ok(tasks)
             }
-            IndexOperation::DocumentEdition { index_uid, mut task } => {
+            IndexOperation::DocumentEdition { mut task, .. } => {
                 let (filter, code) = if let KindWithContent::DocumentEdition {
                     filter_expr,
                     context: _,
@@ -1377,11 +1342,16 @@ impl IndexScheduler {
                 };
 
                 let candidates = match filter.as_ref().map(Filter::from_json) {
-                    Some(Ok(Some(filter))) => filter
-                        .evaluate(index_wtxn, index)
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
+                    Some(Ok(Some(filter))) => {
+                        filter.evaluate(index_wtxn, index).map_err(|err| match err {
+                            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
+                                Error::from(err).with_custom_error_code(Code::InvalidDocumentFilter)
+                            }
+                            e => e.into(),
+                        })?
+                    }
                     None | Some(Ok(None)) => index.documents_ids(index_wtxn)?,
-                    Some(Err(e)) => return Err(Error::from_milli(e, Some(index_uid.clone()))),
+                    Some(Err(e)) => return Err(e.into()),
                 };
 
                 let (original_filter, context, function) = if let Some(Details::DocumentEdition {
@@ -1416,9 +1386,8 @@ impl IndexScheduler {
                 // candidates not empty => index not empty => a primary key is set
                 let primary_key = index.primary_key(&rtxn)?.unwrap();
 
-                let primary_key =
-                    PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
-                        .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
+                let primary_key = PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
+                    .map_err(milli::Error::from)?;
 
                 let result_count = Ok((candidates.len(), candidates.len())) as Result<_>;
 
@@ -1437,17 +1406,11 @@ impl IndexScheduler {
                     };
 
                     let indexer = UpdateByFunction::new(candidates, context.clone(), code.clone());
-                    let document_changes = pool
-                        .install(|| {
-                            indexer
-                                .into_changes(&primary_key)
-                                .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))
-                        })
-                        .unwrap()?;
-                    let embedders = index
-                        .embedding_configs(index_wtxn)
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
-                    let embedders = self.embedders(index_uid.clone(), embedders)?;
+                    let document_changes =
+                        pool.install(|| indexer.into_changes(&primary_key)).unwrap()?;
+
+                    let embedders = index.embedding_configs(index_wtxn)?;
+                    let embedders = self.embedders(embedders)?;
 
                     indexer::index(
                         index_wtxn,
@@ -1461,8 +1424,7 @@ impl IndexScheduler {
                         embedders,
                         &|| must_stop_processing.get(),
                         &send_progress,
-                    )
-                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                    )?;
 
                     // tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
@@ -1493,7 +1455,7 @@ impl IndexScheduler {
 
                 Ok(vec![task])
             }
-            IndexOperation::DocumentDeletion { mut tasks, index_uid } => {
+            IndexOperation::DocumentDeletion { mut tasks, index_uid: _ } => {
                 let mut to_delete = RoaringBitmap::new();
                 let external_documents_ids = index.external_documents_ids();
 
@@ -1514,23 +1476,35 @@ impl IndexScheduler {
                                 deleted_documents: Some(will_be_removed),
                             });
                         }
-                        KindWithContent::DocumentDeletionByFilter { index_uid, filter_expr } => {
+                        KindWithContent::DocumentDeletionByFilter { index_uid: _, filter_expr } => {
                             let before = to_delete.len();
                             let filter = match Filter::from_json(filter_expr) {
                                 Ok(filter) => filter,
                                 Err(err) => {
                                     // theorically, this should be catched by deserr before reaching the index-scheduler and cannot happens
                                     task.status = Status::Failed;
-                                    task.error = Some(
-                                        Error::from_milli(err, Some(index_uid.clone())).into(),
-                                    );
+                                    task.error = match err {
+                                        milli::Error::UserError(
+                                            milli::UserError::InvalidFilterExpression { .. },
+                                        ) => Some(
+                                            Error::from(err)
+                                                .with_custom_error_code(Code::InvalidDocumentFilter)
+                                                .into(),
+                                        ),
+                                        e => Some(e.into()),
+                                    };
                                     None
                                 }
                             };
                             if let Some(filter) = filter {
-                                let candidates = filter
-                                    .evaluate(index_wtxn, index)
-                                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())));
+                                let candidates =
+                                    filter.evaluate(index_wtxn, index).map_err(|err| match err {
+                                        milli::Error::UserError(
+                                            milli::UserError::InvalidFilter(_),
+                                        ) => Error::from(err)
+                                            .with_custom_error_code(Code::InvalidDocumentFilter),
+                                        e => e.into(),
+                                    });
                                 match candidates {
                                     Ok(candidates) => to_delete |= candidates,
                                     Err(err) => {
@@ -1566,9 +1540,8 @@ impl IndexScheduler {
                 // to_delete not empty => index not empty => primary key set
                 let primary_key = index.primary_key(&rtxn)?.unwrap();
 
-                let primary_key =
-                    PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
-                        .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
+                let primary_key = PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
+                    .map_err(milli::Error::from)?;
 
                 if !tasks.iter().all(|res| res.error.is_some()) {
                     let local_pool;
@@ -1587,10 +1560,8 @@ impl IndexScheduler {
                     let mut indexer = indexer::DocumentDeletion::new();
                     indexer.delete_documents_by_docids(to_delete);
                     let document_changes = indexer.into_changes(&indexer_alloc, primary_key);
-                    let embedders = index
-                        .embedding_configs(index_wtxn)
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
-                    let embedders = self.embedders(index_uid.clone(), embedders)?;
+                    let embedders = index.embedding_configs(index_wtxn)?;
+                    let embedders = self.embedders(embedders)?;
 
                     indexer::index(
                         index_wtxn,
@@ -1604,15 +1575,14 @@ impl IndexScheduler {
                         embedders,
                         &|| must_stop_processing.get(),
                         &send_progress,
-                    )
-                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                    )?;
 
                     // tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
 
                 Ok(tasks)
             }
-            IndexOperation::Settings { index_uid, settings, mut tasks } => {
+            IndexOperation::Settings { index_uid: _, settings, mut tasks } => {
                 let indexer_config = self.index_mapper.indexer_config();
                 let mut builder = milli::update::Settings::new(index_wtxn, index, indexer_config);
 
@@ -1626,12 +1596,10 @@ impl IndexScheduler {
                     task.status = Status::Succeeded;
                 }
 
-                builder
-                    .execute(
+                builder.execute(
                     |indexing_step| tracing::debug!(update = ?indexing_step),
                     || must_stop_processing.get(),
-                    )
-                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                )?;
 
                 Ok(tasks)
             }

crates/index-scheduler/src/error.rs

@@ -1,12 +1,13 @@
 use std::fmt::Display;
 
-use crate::TaskId;
 use meilisearch_types::batches::BatchId;
 use meilisearch_types::error::{Code, ErrorCode};
 use meilisearch_types::tasks::{Kind, Status};
 use meilisearch_types::{heed, milli};
 use thiserror::Error;
 
+use crate::TaskId;
+
 #[derive(Copy, Clone, Debug, PartialEq, Eq)]
 pub enum DateField {
     BeforeEnqueuedAt,
@@ -121,11 +122,8 @@ pub enum Error {
     Dump(#[from] dump::Error),
     #[error(transparent)]
     Heed(#[from] heed::Error),
-    #[error("{}", match .index_uid {
-        Some(uid) if !uid.is_empty() => format!("Index `{}`: {error}", uid),
-        _ => format!("{error}")
-    })]
-    Milli { error: milli::Error, index_uid: Option<String> },
+    #[error(transparent)]
+    Milli(#[from] milli::Error),
     #[error("An unexpected crash occurred when processing the task.")]
     ProcessBatchPanicked,
     #[error(transparent)]
@@ -192,7 +190,7 @@ impl Error {
             | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
-            | Error::Milli { .. }
+            | Error::Milli(_)
             | Error::ProcessBatchPanicked
             | Error::FileStore(_)
             | Error::IoError(_)
@@ -211,20 +209,6 @@ impl Error {
     pub fn with_custom_error_code(self, code: Code) -> Self {
         Self::WithCustomErrorCode(code, Box::new(self))
     }
-
-    pub fn from_milli(err: milli::Error, index_uid: Option<String>) -> Self {
-        match err {
-            milli::Error::UserError(milli::UserError::InvalidFilter(_)) => {
-                Self::Milli { error: err, index_uid }
-                    .with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            milli::Error::UserError(milli::UserError::InvalidFilterExpression { .. }) => {
-                Self::Milli { error: err, index_uid }
-                    .with_custom_error_code(Code::InvalidDocumentFilter)
-            }
-            _ => Self::Milli { error: err, index_uid },
-        }
-    }
 }
 
 impl ErrorCode for Error {
@@ -252,7 +236,7 @@ impl ErrorCode for Error {
             // TODO: not sure of the Code to use
             Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
             Error::Dump(e) => e.error_code(),
-            Error::Milli { error, .. } => error.error_code(),
+            Error::Milli(e) => e.error_code(),
             Error::ProcessBatchPanicked => Code::Internal,
             Error::Heed(e) => e.error_code(),
             Error::HeedTransaction(e) => e.error_code(),

crates/index-scheduler/src/index_mapper/index_map.rs

@@ -3,13 +3,14 @@ use std::path::Path;
 use std::time::Duration;
 
 use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
-use meilisearch_types::milli::{Index, Result};
+use meilisearch_types::milli::Index;
 use time::OffsetDateTime;
 use uuid::Uuid;
 
 use super::IndexStatus::{self, Available, BeingDeleted, Closing, Missing};
-use crate::clamp_to_page_size;
 use crate::lru::{InsertionOutcome, LruMap};
+use crate::{clamp_to_page_size, Result};
+
 /// Keep an internally consistent view of the open indexes in memory.
 ///
 /// This view is made of an LRU cache that will evict the least frequently used indexes when new indexes are opened.

crates/index-scheduler/src/index_mapper/mod.rs

@@ -3,13 +3,8 @@ use std::sync::{Arc, RwLock};
 use std::time::Duration;
 use std::{fs, thread};
 
-use self::index_map::IndexMap;
-use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
-use crate::uuid_codec::UuidCodec;
-use crate::{Error, Result};
 use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
-use meilisearch_types::milli;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::{FieldDistribution, Index};
 use serde::{Deserialize, Serialize};
@@ -17,6 +12,11 @@ use time::OffsetDateTime;
 use tracing::error;
 use uuid::Uuid;
 
+use self::index_map::IndexMap;
+use self::IndexStatus::{Available, BeingDeleted, Closing, Missing};
+use crate::uuid_codec::UuidCodec;
+use crate::{Error, Result};
+
 mod index_map;
 
 const INDEX_MAPPING: &str = "index-mapping";
@@ -121,7 +121,7 @@ impl IndexStats {
     /// # Parameters
     ///
     /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
-    pub fn new(index: &Index, rtxn: &RoTxn) -> milli::Result<Self> {
+    pub fn new(index: &Index, rtxn: &RoTxn) -> Result<Self> {
         Ok(IndexStats {
             number_of_documents: index.number_of_documents(rtxn)?,
             database_size: index.on_disk_size()?,
@@ -183,18 +183,13 @@ impl IndexMapper {
                 // Error if the UUIDv4 somehow already exists in the map, since it should be fresh.
                 // This is very unlikely to happen in practice.
                 // TODO: it would be better to lazily create the index. But we need an Index::open function for milli.
-                let index = self
-                    .index_map
-                    .write()
-                    .unwrap()
-                    .create(
+                let index = self.index_map.write().unwrap().create(
                     &uuid,
                     &index_path,
                     date,
                     self.enable_mdb_writemap,
                     self.index_base_map_size,
-                    )
-                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
+                )?;
 
                 wtxn.commit()?;
 
@@ -362,9 +357,7 @@ impl IndexMapper {
                     };
                     let index_path = self.base_path.join(uuid.to_string());
                     // take the lock to reopen the environment.
-                    reopen
-                        .reopen(&mut self.index_map.write().unwrap(), &index_path)
-                        .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
+                    reopen.reopen(&mut self.index_map.write().unwrap(), &index_path)?;
                     continue;
                 }
                 BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
@@ -379,15 +372,13 @@ impl IndexMapper {
                         Missing => {
                             let index_path = self.base_path.join(uuid.to_string());
 
-                            break index_map
-                                .create(
+                            break index_map.create(
                                 &uuid,
                                 &index_path,
                                 None,
                                 self.enable_mdb_writemap,
                                 self.index_base_map_size,
-                                )
-                                .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
+                            )?;
                         }
                         Available(index) => break index,
                         Closing(_) => {
@@ -469,7 +460,6 @@ impl IndexMapper {
                 let index = self.index(rtxn, index_uid)?;
                 let index_rtxn = index.read_txn()?;
                 IndexStats::new(&index, &index_rtxn)
-                    .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))
             }
         }
     }

crates/index-scheduler/src/lib.rs

@@ -1678,10 +1678,9 @@ impl IndexScheduler {
                 tracing::info!("A batch of tasks was successfully completed with {success} successful tasks and {failure} failed tasks.");
             }
             // If we have an abortion error we must stop the tick here and re-schedule tasks.
-            Err(Error::Milli {
-                error: milli::Error::InternalError(milli::InternalError::AbortedIndexation),
-                ..
-            })
+            Err(Error::Milli(milli::Error::InternalError(
+                milli::InternalError::AbortedIndexation,
+            )))
             | Err(Error::AbortedTask) => {
                 #[cfg(test)]
                 self.breakpoint(Breakpoint::AbortedIndexation);
@@ -1700,10 +1699,9 @@ impl IndexScheduler {
             // 2. close the associated environment
             // 3. resize it
             // 4. re-schedule tasks
-            Err(Error::Milli {
-                error: milli::Error::UserError(milli::UserError::MaxDatabaseSizeReached),
-                ..
-            }) if index_uid.is_some() => {
+            Err(Error::Milli(milli::Error::UserError(
+                milli::UserError::MaxDatabaseSizeReached,
+            ))) if index_uid.is_some() => {
                 // fixme: add index_uid to match to avoid the unwrap
                 let index_uid = index_uid.unwrap();
                 // fixme: handle error more gracefully? not sure when this could happen
@@ -1945,7 +1943,6 @@ impl IndexScheduler {
     // TODO: consider using a type alias or a struct embedder/template
     pub fn embedders(
         &self,
-        index_uid: String,
         embedding_configs: Vec<IndexEmbeddingConfig>,
     ) -> Result<EmbeddingConfigs> {
         let res: Result<_> = embedding_configs
@@ -1956,12 +1953,8 @@ impl IndexScheduler {
                      config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
                      ..
                  }| {
-                    let prompt = Arc::new(
-                        prompt
-                            .try_into()
-                            .map_err(meilisearch_types::milli::Error::from)
-                            .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
-                    );
+                    let prompt =
+                        Arc::new(prompt.try_into().map_err(meilisearch_types::milli::Error::from)?);
                     // optimistically return existing embedder
                     {
                         let embedders = self.embedders.read().unwrap();
@@ -1977,9 +1970,7 @@ impl IndexScheduler {
                     let embedder = Arc::new(
                         Embedder::new(embedder_options.clone())
                             .map_err(meilisearch_types::milli::vector::Error::from)
-                            .map_err(|err| {
-                                Error::from_milli(err.into(), Some(index_uid.clone()))
-                            })?,
+                            .map_err(meilisearch_types::milli::Error::from)?,
                     );
                     {
                         let mut embedders = self.embedders.write().unwrap();
@@ -6180,7 +6171,7 @@ mod tests {
             insta::assert_json_snapshot!(simple_hf_config.embedder_options);
             let simple_hf_name = name.clone();
 
-            let configs = index_scheduler.embedders("doggos".to_string(), configs).unwrap();
+            let configs = index_scheduler.embedders(configs).unwrap();
             let (hf_embedder, _, _) = configs.get(&simple_hf_name).unwrap();
             let beagle_embed =
                 hf_embedder.embed_one(S("Intel the beagle best doggo"), None).unwrap();

crates/index-scheduler/src/snapshots/lib.rs/fail_in_process_batch_for_document_deletion/after_removing_the_documents.snap

@@ -9,8 +9,8 @@ source: crates/index-scheduler/src/lib.rs
 0 {uid: 0, batch_uid: 0, status: succeeded, details: { settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> } }, kind: SettingsUpdate { index_uid: "doggos", new_settings: Settings { displayed_attributes: WildcardSetting(NotSet), searchable_attributes: WildcardSetting(NotSet), filterable_attributes: Set({"catto"}), sortable_attributes: NotSet, ranking_rules: NotSet, stop_words: NotSet, non_separator_tokens: NotSet, separator_tokens: NotSet, dictionary: NotSet, synonyms: NotSet, distinct_attribute: NotSet, proximity_precision: NotSet, typo_tolerance: NotSet, faceting: NotSet, pagination: NotSet, embedders: NotSet, search_cutoff_ms: NotSet, localized_attributes: NotSet, facet_search: NotSet, prefix_search: NotSet, _kind: PhantomData<meilisearch_types::settings::Unchecked> }, is_deletion: false, allow_index_creation: true }}
 1 {uid: 1, batch_uid: 1, status: succeeded, details: { received_documents: 3, indexed_documents: Some(3) }, kind: DocumentAdditionOrUpdate { index_uid: "doggos", primary_key: Some("id"), method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 3, allow_index_creation: true }}
 2 {uid: 2, batch_uid: 2, status: succeeded, details: { received_document_ids: 1, deleted_documents: Some(1) }, kind: DocumentDeletion { index_uid: "doggos", documents_ids: ["1"] }}
-3 {uid: 3, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
-4 {uid: 4, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Index `doggos`: Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
+3 {uid: 3, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Invalid type for filter subexpression: expected: String, Array, found: true.", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: true, deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: Bool(true) }}
+4 {uid: 4, batch_uid: 2, status: failed, error: ResponseError { code: 200, message: "Attribute `id` is not filterable. Available filterable attributes are: `catto`.\n1:3 id = 2", error_code: "invalid_document_filter", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#invalid_document_filter" }, details: { original_filter: "id = 2", deleted_documents: Some(0) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("id = 2") }}
 5 {uid: 5, batch_uid: 2, status: succeeded, details: { original_filter: "catto EXISTS", deleted_documents: Some(1) }, kind: DocumentDeletionByFilter { index_uid: "doggos", filter_expr: String("catto EXISTS") }}
 ----------------------------------------------------------------------
 ### Status:

crates/meilisearch/src/error.rs

@@ -4,7 +4,6 @@ use byte_unit::{Byte, UnitType};
 use meilisearch_types::document_formats::{DocumentFormatError, PayloadType};
 use meilisearch_types::error::{Code, ErrorCode, ResponseError};
 use meilisearch_types::index_uid::{IndexUid, IndexUidFormatError};
-use meilisearch_types::milli;
 use meilisearch_types::milli::OrderBy;
 use serde_json::Value;
 use tokio::task::JoinError;
@@ -63,11 +62,8 @@ pub enum MeilisearchHttpError {
     HeedError(#[from] meilisearch_types::heed::Error),
     #[error(transparent)]
     IndexScheduler(#[from] index_scheduler::Error),
-    #[error("{}", match .index_name {
-        Some(name) if !name.is_empty() => format!("Index `{}`: {error}", name),
-        _ => format!("{error}")
-    })]
-    Milli { error: milli::Error, index_name: Option<String> },
+    #[error(transparent)]
+    Milli(#[from] meilisearch_types::milli::Error),
     #[error(transparent)]
     Payload(#[from] PayloadError),
     #[error(transparent)]
@@ -80,12 +76,6 @@ pub enum MeilisearchHttpError {
     MissingSearchHybrid,
 }
 
-impl MeilisearchHttpError {
-    pub(crate) fn from_milli(error: milli::Error, index_name: Option<String>) -> Self {
-        Self::Milli { error, index_name }
-    }
-}
-
 impl ErrorCode for MeilisearchHttpError {
     fn error_code(&self) -> Code {
         match self {
@@ -105,7 +95,7 @@ impl ErrorCode for MeilisearchHttpError {
             MeilisearchHttpError::SerdeJson(_) => Code::Internal,
             MeilisearchHttpError::HeedError(_) => Code::Internal,
             MeilisearchHttpError::IndexScheduler(e) => e.error_code(),
-            MeilisearchHttpError::Milli { error, .. } => error.error_code(),
+            MeilisearchHttpError::Milli(e) => e.error_code(),
             MeilisearchHttpError::Payload(e) => e.error_code(),
             MeilisearchHttpError::FileStore(_) => Code::Internal,
             MeilisearchHttpError::DocumentFormat(e) => e.error_code(),

crates/meilisearch/src/lib.rs

@@ -395,7 +395,6 @@ fn import_dump(
     for index_reader in dump_reader.indexes()? {
         let mut index_reader = index_reader?;
         let metadata = index_reader.metadata();
-        let uid = metadata.uid.clone();
         tracing::info!("Importing index `{}`.", metadata.uid);
 
         let date = Some((metadata.created_at, metadata.updated_at));
@@ -433,7 +432,7 @@ fn import_dump(
         let reader = DocumentsBatchReader::from_reader(reader)?;
 
         let embedder_configs = index.embedding_configs(&wtxn)?;
-        let embedders = index_scheduler.embedders(uid, embedder_configs)?;
+        let embedders = index_scheduler.embedders(embedder_configs)?;
 
         let builder = milli::update::IndexDocuments::new(
             &mut wtxn,

crates/meilisearch/src/option.rs

@@ -654,8 +654,9 @@ impl Opt {
 
 #[derive(Debug, Default, Clone, Parser, Deserialize)]
 pub struct IndexerOpts {
-    /// Sets the maximum amount of RAM Meilisearch can use when indexing. By default, Meilisearch
-    /// uses no more than two thirds of available memory.
+    /// Specifies the maximum resident memory that Meilisearch can use for indexing.
+    /// By default, Meilisearch limits the RAM usage to 5% of the total available memory.
+    /// Note that the underlying store utilizes memory-mapping and makes use of the rest.
     #[clap(long, env = MEILI_MAX_INDEXING_MEMORY, default_value_t)]
     #[serde(default)]
     pub max_indexing_memory: MaxMemory,
@@ -714,7 +715,7 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
     }
 }
 
-/// A type used to detect the max memory available and use 2/3 of it.
+/// A type used to detect the max resident memory available and use 5% of it.
 #[derive(Debug, Clone, Copy, Deserialize, Serialize)]
 pub struct MaxMemory(Option<Byte>);
 
@@ -728,7 +729,7 @@ impl FromStr for MaxMemory {
 
 impl Default for MaxMemory {
     fn default() -> MaxMemory {
-        MaxMemory(total_memory_bytes().map(|bytes| bytes * 2 / 3).map(Byte::from_u64))
+        MaxMemory(total_memory_bytes().map(|bytes| bytes * 5 / 100).map(Byte::from_u64))
     }
 }
 

crates/meilisearch/src/routes/indexes/facet_search.rs

@@ -185,8 +185,7 @@ pub async fn search(
 
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
-    let search_kind =
-        search_kind(&search_query, &index_scheduler, index_uid.to_string(), &index, features)?;
+    let search_kind = search_kind(&search_query, &index_scheduler, &index, features)?;
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
         perform_facet_search(

crates/meilisearch/src/routes/indexes/mod.rs

@@ -5,7 +5,7 @@ use actix_web::web::Data;
 use actix_web::{web, HttpRequest, HttpResponse};
 use deserr::actix_web::{AwebJson, AwebQueryParameter};
 use deserr::{DeserializeError, Deserr, ValuePointerRef};
-use index_scheduler::{Error, IndexScheduler};
+use index_scheduler::IndexScheduler;
 use meilisearch_types::deserr::query_params::Param;
 use meilisearch_types::deserr::{immutable_field_error, DeserrJsonError, DeserrQueryParamError};
 use meilisearch_types::error::deserr_codes::*;
@@ -107,10 +107,7 @@ pub async fn list_indexes(
             if !filters.is_index_authorized(uid) {
                 return Ok(None);
             }
-            Ok(Some(
-                IndexView::new(uid.to_string(), index)
-                    .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?,
-            ))
+            Ok(Some(IndexView::new(uid.to_string(), index)?))
         })?;
     // Won't cause to open all indexes because IndexView doesn't keep the `Index` opened.
     let indexes: Vec<IndexView> = indexes.into_iter().flatten().collect();

crates/meilisearch/src/routes/indexes/search.rs

@@ -243,19 +243,11 @@ pub async fn search_with_url_query(
     let index = index_scheduler.index(&index_uid)?;
     let features = index_scheduler.features();
 
-    let search_kind =
-        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index, features)?;
+    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)?;
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
-        perform_search(
-            index_uid.to_string(),
-            &index,
-            query,
-            search_kind,
-            retrieve_vector,
-            index_scheduler.features(),
-        )
+        perform_search(&index, query, search_kind, retrieve_vector, index_scheduler.features())
     })
     .await;
     permit.drop().await;
@@ -295,20 +287,12 @@ pub async fn search_with_post(
 
     let features = index_scheduler.features();
 
-    let search_kind =
-        search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index, features)?;
+    let search_kind = search_kind(&query, index_scheduler.get_ref(), &index, features)?;
     let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors, features)?;
 
     let permit = search_queue.try_get_search_permit().await?;
     let search_result = tokio::task::spawn_blocking(move || {
-        perform_search(
-            index_uid.to_string(),
-            &index,
-            query,
-            search_kind,
-            retrieve_vectors,
-            index_scheduler.features(),
-        )
+        perform_search(&index, query, search_kind, retrieve_vectors, index_scheduler.features())
     })
     .await;
     permit.drop().await;
@@ -330,7 +314,6 @@ pub async fn search_with_post(
 pub fn search_kind(
     query: &SearchQuery,
     index_scheduler: &IndexScheduler,
-    index_uid: String,
     index: &milli::Index,
     features: RoFeatures,
 ) -> Result<SearchKind, ResponseError> {
@@ -349,7 +332,7 @@ pub fn search_kind(
         (None, _, None) => Ok(SearchKind::KeywordOnly),
         // hybrid.semantic_ratio == 1.0 => vector
         (_, Some(HybridQuery { semantic_ratio, embedder }), v) if **semantic_ratio == 1.0 => {
-            SearchKind::semantic(index_scheduler, index_uid, index, embedder, v.map(|v| v.len()))
+            SearchKind::semantic(index_scheduler, index, embedder, v.map(|v| v.len()))
         }
         // hybrid.semantic_ratio == 0.0 => keyword
         (_, Some(HybridQuery { semantic_ratio, embedder: _ }), _) if **semantic_ratio == 0.0 => {
@@ -357,14 +340,13 @@ pub fn search_kind(
         }
         // no query, hybrid, vector => semantic
         (None, Some(HybridQuery { semantic_ratio: _, embedder }), Some(v)) => {
-            SearchKind::semantic(index_scheduler, index_uid, index, embedder, Some(v.len()))
+            SearchKind::semantic(index_scheduler, index, embedder, Some(v.len()))
         }
         // query, no hybrid, no vector => keyword
         (Some(_), None, None) => Ok(SearchKind::KeywordOnly),
         // query, hybrid, maybe vector => hybrid
         (Some(_), Some(HybridQuery { semantic_ratio, embedder }), v) => SearchKind::hybrid(
             index_scheduler,
-            index_uid,
             index,
             embedder,
             **semantic_ratio,

crates/meilisearch/src/routes/indexes/similar.rs

@@ -103,13 +103,8 @@ async fn similar(
 
     let index = index_scheduler.index(&index_uid)?;
 
-    let (embedder_name, embedder, quantized) = SearchKind::embedder(
-        &index_scheduler,
-        index_uid.to_string(),
-        &index,
-        &query.embedder,
-        None,
-    )?;
+    let (embedder_name, embedder, quantized) =
+        SearchKind::embedder(&index_scheduler, &index, &query.embedder, None)?;
 
     tokio::task::spawn_blocking(move || {
         perform_similar(

crates/meilisearch/src/routes/multi_search.rs

@@ -125,28 +125,14 @@ pub async fn multi_search_with_post(
                         })
                         .with_index(query_index)?;
 
-                    let index_uid_str = index_uid.to_string();
-
-                    let search_kind = search_kind(
-                        &query,
-                        index_scheduler.get_ref(),
-                        index_uid_str.clone(),
-                        &index,
-                        features,
-                    )
+                    let search_kind =
+                        search_kind(&query, index_scheduler.get_ref(), &index, features)
                             .with_index(query_index)?;
                     let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors, features)
                         .with_index(query_index)?;
 
                     let search_result = tokio::task::spawn_blocking(move || {
-                        perform_search(
-                            index_uid_str.clone(),
-                            &index,
-                            query,
-                            search_kind,
-                            retrieve_vector,
-                            features,
-                        )
+                        perform_search(&index, query, search_kind, retrieve_vector, features)
                     })
                     .await
                     .with_index(query_index)?;

crates/meilisearch/src/search/federated.rs

@@ -560,8 +560,7 @@ pub fn perform_federated_search(
             // use an immediately invoked lambda to capture the result without returning from the function
 
             let res: Result<(), ResponseError> = (|| {
-                let search_kind =
-                    search_kind(&query, index_scheduler, index_uid.to_string(), &index, features)?;
+                let search_kind = search_kind(&query, index_scheduler, &index, features)?;
 
                 let canonicalization_kind = match (&search_kind, &query.q) {
                     (SearchKind::SemanticOnly { .. }, _) => {
@@ -637,8 +636,7 @@ pub fn perform_federated_search(
                 search.offset(0);
                 search.limit(required_hit_count);
 
-                let (result, _semantic_hit_count) =
-                    super::search_from_kind(index_uid.to_string(), search_kind, search)?;
+                let (result, _semantic_hit_count) = super::search_from_kind(search_kind, search)?;
                 let format = AttributesFormat {
                     attributes_to_retrieve: query.attributes_to_retrieve,
                     retrieve_vectors,
@@ -672,10 +670,7 @@ pub fn perform_federated_search(
 
                 let formatter_builder = HitMaker::formatter_builder(matching_words, tokenizer);
 
-                let hit_maker =
-                    HitMaker::new(&index, &rtxn, format, formatter_builder).map_err(|e| {
-                        MeilisearchHttpError::from_milli(e, Some(index_uid.to_string()))
-                    })?;
+                let hit_maker = HitMaker::new(&index, &rtxn, format, formatter_builder)?;
 
                 results_by_query.push(SearchResultByQuery {
                     federation_options,

crates/meilisearch/src/search/mod.rs

@@ -19,9 +19,7 @@ use meilisearch_types::locales::Locale;
 use meilisearch_types::milli::score_details::{ScoreDetails, ScoringStrategy};
 use meilisearch_types::milli::vector::parsed_vectors::ExplicitVectors;
 use meilisearch_types::milli::vector::Embedder;
-use meilisearch_types::milli::{
-    FacetValueHit, InternalError, OrderBy, SearchForFacetValues, TimeBudget,
-};
+use meilisearch_types::milli::{FacetValueHit, OrderBy, SearchForFacetValues, TimeBudget};
 use meilisearch_types::settings::DEFAULT_PAGINATION_MAX_TOTAL_HITS;
 use meilisearch_types::{milli, Document};
 use milli::tokenizer::{Language, TokenizerBuilder};
@@ -283,38 +281,35 @@ pub enum SearchKind {
 impl SearchKind {
     pub(crate) fn semantic(
         index_scheduler: &index_scheduler::IndexScheduler,
-        index_uid: String,
         index: &Index,
         embedder_name: &str,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
         let (embedder_name, embedder, quantized) =
-            Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
+            Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
         Ok(Self::SemanticOnly { embedder_name, embedder, quantized })
     }
 
     pub(crate) fn hybrid(
         index_scheduler: &index_scheduler::IndexScheduler,
-        index_uid: String,
         index: &Index,
         embedder_name: &str,
         semantic_ratio: f32,
         vector_len: Option<usize>,
     ) -> Result<Self, ResponseError> {
         let (embedder_name, embedder, quantized) =
-            Self::embedder(index_scheduler, index_uid, index, embedder_name, vector_len)?;
+            Self::embedder(index_scheduler, index, embedder_name, vector_len)?;
         Ok(Self::Hybrid { embedder_name, embedder, quantized, semantic_ratio })
     }
 
     pub(crate) fn embedder(
         index_scheduler: &index_scheduler::IndexScheduler,
-        index_uid: String,
         index: &Index,
         embedder_name: &str,
         vector_len: Option<usize>,
     ) -> Result<(String, Arc<Embedder>, bool), ResponseError> {
         let embedder_configs = index.embedding_configs(&index.read_txn()?)?;
-        let embedders = index_scheduler.embedders(index_uid, embedder_configs)?;
+        let embedders = index_scheduler.embedders(embedder_configs)?;
 
         let (embedder, _, quantized) = embedders
             .get(embedder_name)
@@ -895,7 +890,6 @@ fn prepare_search<'t>(
 }
 
 pub fn perform_search(
-    index_uid: String,
     index: &Index,
     query: SearchQuery,
     search_kind: SearchKind,
@@ -922,7 +916,7 @@ pub fn perform_search(
             used_negative_operator,
         },
         semantic_hit_count,
-    ) = search_from_kind(index_uid, search_kind, search)?;
+    ) = search_from_kind(search_kind, search)?;
 
     let SearchQuery {
         q,
@@ -1075,27 +1069,17 @@ fn compute_facet_distribution_stats<S: AsRef<str>>(
 }
 
 pub fn search_from_kind(
-    index_uid: String,
     search_kind: SearchKind,
     search: milli::Search<'_>,
 ) -> Result<(milli::SearchResult, Option<u32>), MeilisearchHttpError> {
     let (milli_result, semantic_hit_count) = match &search_kind {
-        SearchKind::KeywordOnly => {
-            let results = search
-                .execute()
-                .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
-            (results, None)
-        }
+        SearchKind::KeywordOnly => (search.execute()?, None),
         SearchKind::SemanticOnly { .. } => {
-            let results = search
-                .execute()
-                .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid.to_string())))?;
+            let results = search.execute()?;
             let semantic_hit_count = results.document_scores.len() as u32;
             (results, Some(semantic_hit_count))
         }
-        SearchKind::Hybrid { semantic_ratio, .. } => search
-            .execute_hybrid(*semantic_ratio)
-            .map_err(|e| MeilisearchHttpError::from_milli(e, Some(index_uid)))?,
+        SearchKind::Hybrid { semantic_ratio, .. } => search.execute_hybrid(*semantic_ratio)?,
     };
     Ok((milli_result, semantic_hit_count))
 }
@@ -1197,7 +1181,7 @@ impl<'a> HitMaker<'a> {
         rtxn: &'a RoTxn<'a>,
         format: AttributesFormat,
         mut formatter_builder: MatcherBuilder<'a>,
-    ) -> milli::Result<Self> {
+    ) -> Result<Self, MeilisearchHttpError> {
         formatter_builder.crop_marker(format.crop_marker);
         formatter_builder.highlight_prefix(format.highlight_pre_tag);
         formatter_builder.highlight_suffix(format.highlight_post_tag);
@@ -1292,7 +1276,11 @@ impl<'a> HitMaker<'a> {
         })
     }
 
-    pub fn make_hit(&self, id: u32, score: &[ScoreDetails]) -> milli::Result<SearchHit> {
+    pub fn make_hit(
+        &self,
+        id: u32,
+        score: &[ScoreDetails],
+    ) -> Result<SearchHit, MeilisearchHttpError> {
         let (_, obkv) =
             self.index.iter_documents(self.rtxn, std::iter::once(id))?.next().unwrap()?;
 
@@ -1335,10 +1323,7 @@ impl<'a> HitMaker<'a> {
                     .is_some_and(|conf| conf.user_provided.contains(id));
                 let embeddings =
                     ExplicitVectors { embeddings: Some(vector.into()), regenerate: !user_provided };
-                vectors.insert(
-                    name,
-                    serde_json::to_value(embeddings).map_err(InternalError::SerdeJson)?,
-                );
+                vectors.insert(name, serde_json::to_value(embeddings)?);
             }
             document.insert("_vectors".into(), vectors.into());
         }
@@ -1384,7 +1369,7 @@ fn make_hits<'a>(
     format: AttributesFormat,
     matching_words: milli::MatchingWords,
     documents_ids_scores: impl Iterator<Item = (u32, &'a Vec<ScoreDetails>)> + 'a,
-) -> milli::Result<Vec<SearchHit>> {
+) -> Result<Vec<SearchHit>, MeilisearchHttpError> {
     let mut documents = Vec::new();
 
     let dictionary = index.dictionary(rtxn)?;
@@ -1712,12 +1697,12 @@ fn make_document(
     displayed_attributes: &BTreeSet<FieldId>,
     field_ids_map: &FieldsIdsMap,
     obkv: &obkv::KvReaderU16,
-) -> milli::Result<Document> {
+) -> Result<Document, MeilisearchHttpError> {
     let mut document = serde_json::Map::new();
 
     // recreate the original json
     for (key, value) in obkv.iter() {
-        let value = serde_json::from_slice(value).map_err(InternalError::SerdeJson)?;
+        let value = serde_json::from_slice(value)?;
         let key = field_ids_map.name(key).expect("Missing field name").to_string();
 
         document.insert(key, value);
@@ -1742,7 +1727,7 @@ fn format_fields(
     displayable_ids: &BTreeSet<FieldId>,
     locales: Option<&[Language]>,
     localized_attributes: &[LocalizedAttributesRule],
-) -> milli::Result<(Option<MatchesPosition>, Document)> {
+) -> Result<(Option<MatchesPosition>, Document), MeilisearchHttpError> {
     let mut matches_position = compute_matches.then(BTreeMap::new);
     let mut document = document.clone();
 
@@ -1920,7 +1905,7 @@ fn parse_filter_array(arr: &[Value]) -> Result<Option<Filter>, MeilisearchHttpEr
         }
     }
 
-    Filter::from_array(ands).map_err(|e| MeilisearchHttpError::from_milli(e, None))
+    Ok(Filter::from_array(ands)?)
 }
 
 #[cfg(test)]

crates/meilisearch/tests/documents/add_documents.rs

@@ -1681,7 +1681,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: The `_geo` field in the document with the id: `\"11\"` is not an object. Was expecting an object with the `_geo.lat` and `_geo.lng` fields but instead got `\"foobar\"`.",
+        "message": "The `_geo` field in the document with the id: `\"11\"` is not an object. Was expecting an object with the `_geo.lat` and `_geo.lng` fields but instead got `\"foobar\"`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1719,7 +1719,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find latitude nor longitude in the document with the id: `\"11\"`. Was expecting `_geo.lat` and `_geo.lng` fields.",
+        "message": "Could not find latitude nor longitude in the document with the id: `\"11\"`. Was expecting `_geo.lat` and `_geo.lng` fields.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1757,7 +1757,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find latitude nor longitude in the document with the id: `\"11\"`. Was expecting `_geo.lat` and `_geo.lng` fields.",
+        "message": "Could not find latitude nor longitude in the document with the id: `\"11\"`. Was expecting `_geo.lat` and `_geo.lng` fields.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1795,7 +1795,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
+        "message": "Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1833,7 +1833,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
+        "message": "Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1871,7 +1871,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
+        "message": "Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1909,7 +1909,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
+        "message": "Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1947,7 +1947,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not parse latitude nor longitude in the document with the id: `\"11\"`. Was expecting finite numbers but instead got `false` and `true`.",
+        "message": "Could not parse latitude nor longitude in the document with the id: `\"11\"`. Was expecting finite numbers but instead got `false` and `true`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -1985,7 +1985,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
+        "message": "Could not find longitude in the document with the id: `\"11\"`. Was expecting a `_geo.lng` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2023,7 +2023,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
+        "message": "Could not find latitude in the document with the id: `\"11\"`. Was expecting a `_geo.lat` field.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2061,7 +2061,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not parse latitude nor longitude in the document with the id: `\"11\"`. Was expecting finite numbers but instead got `\"doggo\"` and `\"doggo\"`.",
+        "message": "Could not parse latitude nor longitude in the document with the id: `\"11\"`. Was expecting finite numbers but instead got `\"doggo\"` and `\"doggo\"`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2099,7 +2099,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: The `_geo` field in the document with the id: `\"11\"` contains the following unexpected fields: `{\"doggo\":\"are the best\"}`.",
+        "message": "The `_geo` field in the document with the id: `\"11\"` contains the following unexpected fields: `{\"doggo\":\"are the best\"}`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2138,7 +2138,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not parse longitude in the document with the id: `\"12\"`. Was expecting a finite number but instead got `null`.",
+        "message": "Could not parse longitude in the document with the id: `\"12\"`. Was expecting a finite number but instead got `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2175,7 +2175,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not parse latitude in the document with the id: `\"12\"`. Was expecting a finite number but instead got `null`.",
+        "message": "Could not parse latitude in the document with the id: `\"12\"`. Was expecting a finite number but instead got `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2212,7 +2212,7 @@ async fn add_documents_invalid_geo_field() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `test`: Could not parse latitude nor longitude in the document with the id: `\"13\"`. Was expecting finite numbers but instead got `null` and `null`.",
+        "message": "Could not parse latitude nor longitude in the document with the id: `\"13\"`. Was expecting finite numbers but instead got `null` and `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"
@@ -2279,7 +2279,7 @@ async fn add_invalid_geo_and_then_settings() {
         ]
       },
       "error": {
-        "message": "Index `test`: Could not parse latitude in the document with the id: `\"11\"`. Was expecting a finite number but instead got `null`.",
+        "message": "Could not parse latitude in the document with the id: `\"11\"`. Was expecting a finite number but instead got `null`.",
         "code": "invalid_document_geo_field",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_geo_field"

crates/meilisearch/tests/documents/errors.rs

@@ -604,7 +604,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"doggo = bernese\""
       },
       "error": {
-        "message": "Index `EMPTY_INDEX`: Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
+        "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@@ -636,7 +636,7 @@ async fn delete_document_by_filter() {
         "originalFilter": "\"catto = jorts\""
       },
       "error": {
-        "message": "Index `SHARED_DOCUMENTS`: Attribute `catto` is not filterable. Available filterable attributes are: `id`, `title`.\n1:6 catto = jorts",
+        "message": "Attribute `catto` is not filterable. Available filterable attributes are: `id`, `title`.\n1:6 catto = jorts",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"

crates/meilisearch/tests/index/update_index.rs

@@ -95,7 +95,7 @@ async fn error_update_existing_primary_key() {
     let response = index.wait_task(2).await;
 
     let expected_response = json!({
-        "message": "Index `test`: Index already has a primary key: `id`.",
+        "message": "Index already has a primary key: `id`.",
         "code": "index_primary_key_already_exists",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#index_primary_key_already_exists"

crates/meilisearch/tests/search/errors.rs

@@ -711,7 +711,7 @@ async fn filter_invalid_attribute_array() {
     index.wait_task(task.uid()).await;
 
     let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass", index.uid),
+        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -733,7 +733,7 @@ async fn filter_invalid_attribute_string() {
     index.wait_task(task.uid()).await;
 
     let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass", index.uid),
+        "message": "Attribute `many` is not filterable. Available filterable attributes are: `title`.\n1:5 many = Glass",
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -940,7 +940,7 @@ async fn sort_unsortable_attribute() {
     index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `title` is not sortable. Available sortable attributes are: `id`.", index.uid),
+        "message": "Attribute `title` is not sortable. Available sortable attributes are: `id`.",
         "code": "invalid_search_sort",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -998,7 +998,7 @@ async fn sort_unset_ranking_rule() {
     index.wait_task(response.uid()).await.succeeded();
 
     let expected_response = json!({
-        "message": format!("Index `{}`: You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.", index.uid),
+        "message": "You must specify where `sort` is listed in the rankingRules setting to use the sort parameter at search time.",
         "code": "invalid_search_sort",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1024,18 +1024,19 @@ async fn search_on_unknown_field() {
         index.update_settings_searchable_attributes(json!(["id", "title"])).await;
     index.wait_task(response.uid()).await.succeeded();
 
-    let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.", index.uid),
-        "code": "invalid_search_attributes_to_search_on",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
-    });
     index
         .search(
             json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown"]}),
             |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
+                snapshot!(code, @"400 Bad Request");
+                snapshot!(json_string!(response), @r###"
+                {
+                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
+                  "code": "invalid_search_attributes_to_search_on",
+                  "type": "invalid_request",
+                  "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
+                }
+                "###);
             },
         )
         .await;
@@ -1049,18 +1050,19 @@ async fn search_on_unknown_field_plus_joker() {
         index.update_settings_searchable_attributes(json!(["id", "title"])).await;
     index.wait_task(response.uid()).await.succeeded();
 
-    let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.", index.uid),
-        "code": "invalid_search_attributes_to_search_on",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
-    });
     index
         .search(
             json!({"q": "Captain Marvel", "attributesToSearchOn": ["*", "unknown"]}),
             |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
+                snapshot!(code, @"400 Bad Request");
+                snapshot!(json_string!(response), @r###"
+                {
+                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
+                  "code": "invalid_search_attributes_to_search_on",
+                  "type": "invalid_request",
+                  "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
+                }
+                "###);
             },
         )
         .await;
@@ -1069,8 +1071,15 @@ async fn search_on_unknown_field_plus_joker() {
         .search(
             json!({"q": "Captain Marvel", "attributesToSearchOn": ["unknown", "*"]}),
             |response, code| {
-                assert_eq!(response, expected_response);
-                assert_eq!(code, 400);
+                snapshot!(code, @"400 Bad Request");
+                snapshot!(json_string!(response), @r###"
+                {
+                  "message": "Attribute `unknown` is not searchable. Available searchable attributes are: `id, title`.",
+                  "code": "invalid_search_attributes_to_search_on",
+                  "type": "invalid_request",
+                  "link": "https://docs.meilisearch.com/errors#invalid_search_attributes_to_search_on"
+                }
+                "###);
             },
         )
         .await;
@@ -1083,44 +1092,47 @@ async fn distinct_at_search_time() {
     let (task, _) = index.create(None).await;
     index.wait_task(task.uid()).await.succeeded();
 
-    let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. This index does not have configured filterable attributes.", index.uid),
+    let (response, code) =
+        index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(response, @r###"
+    {
+      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. This index does not have configured filterable attributes.",
       "code": "invalid_search_distinct",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
-    });
-    let (response, code) =
-        index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
-    assert_eq!(response, expected_response);
-    assert_eq!(code, 400);
+    }
+    "###);
 
     let (task, _) = index.update_settings_filterable_attributes(json!(["color", "machin"])).await;
     index.wait_task(task.uid()).await;
 
-    let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, machin`.", index.uid),
+    let (response, code) =
+        index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(response, @r###"
+    {
+      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, machin`.",
       "code": "invalid_search_distinct",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
-    });
-    let (response, code) =
-        index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
-    assert_eq!(response, expected_response);
-    assert_eq!(code, 400);
+    }
+    "###);
 
     let (task, _) = index.update_settings_displayed_attributes(json!(["color"])).await;
     index.wait_task(task.uid()).await;
 
-    let expected_response = json!({
-        "message": format!("Index `{}`: Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, <..hidden-attributes>`.", index.uid),
+    let (response, code) =
+        index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(response, @r###"
+    {
+      "message": "Attribute `doggo.truc` is not filterable and thus, cannot be used as distinct attribute. Available filterable attributes are: `color, <..hidden-attributes>`.",
       "code": "invalid_search_distinct",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_distinct"
-    });
-    let (response, code) =
-        index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": "doggo.truc"})).await;
-    assert_eq!(response, expected_response);
-    assert_eq!(code, 400);
+    }
+    "###);
 
     let (response, code) =
         index.search_post(json!({"page": 0, "hitsPerPage": 2, "distinct": true})).await;

crates/meilisearch/tests/search/multi.rs

@@ -1070,7 +1070,7 @@ async fn federation_one_query_error() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Index `nested`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
+      "message": "Inside `.queries[1]`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1102,7 +1102,7 @@ async fn federation_one_query_sort_error() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[1]`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1166,7 +1166,7 @@ async fn federation_multiple_query_errors() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[0]`: Index `test`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
+      "message": "Inside `.queries[0]`: Attribute `title` is not filterable. This index does not have configured filterable attributes.\n1:6 title = toto",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1198,7 +1198,7 @@ async fn federation_multiple_query_sort_errors() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[0]`: Index `test`: Attribute `title` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[0]`: Attribute `title` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"
@@ -1231,7 +1231,7 @@ async fn federation_multiple_query_errors_interleaved() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not filterable. This index does not have configured filterable attributes.\n1:7 doggos IN [intel, kefir]",
+      "message": "Inside `.queries[1]`: Attribute `doggos` is not filterable. This index does not have configured filterable attributes.\n1:7 doggos IN [intel, kefir]",
       "code": "invalid_search_filter",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -1264,7 +1264,7 @@ async fn federation_multiple_query_sort_errors_interleaved() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Inside `.queries[1]`: Index `nested`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
+      "message": "Inside `.queries[1]`: Attribute `doggos` is not sortable. This index does not have configured sortable attributes.",
       "code": "invalid_search_sort",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_search_sort"

crates/meilisearch/tests/tasks/mod.rs

@@ -448,7 +448,7 @@ async fn test_summarized_delete_documents_by_filter() {
         "originalFilter": "\"doggo = bernese\""
       },
       "error": {
-        "message": "Index `test`: Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
+        "message": "Attribute `doggo` is not filterable. This index does not have configured filterable attributes.\n1:6 doggo = bernese",
         "code": "invalid_document_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_filter"

crates/meilisearch/tests/vector/binary_quantized.rs

@@ -318,7 +318,7 @@ async fn try_to_disable_binary_quantization() {
         }
       },
       "error": {
-        "message": "Index `doggo`: `.embedders.manual.binaryQuantized`: Cannot disable the binary quantization.\n - Note: Binary quantization is a lossy operation that cannot be reverted.\n - Hint: Add a new embedder that is non-quantized and regenerate the vectors.",
+        "message": "`.embedders.manual.binaryQuantized`: Cannot disable the binary quantization.\n - Note: Binary quantization is a lossy operation that cannot be reverted.\n - Hint: Add a new embedder that is non-quantized and regenerate the vectors.",
         "code": "invalid_settings_embedders",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"

crates/meilisearch/tests/vector/mod.rs

@@ -250,7 +250,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n  - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
+        "message": "Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n  - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -280,7 +280,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n  - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
+        "message": "Bad embedder configuration in the document with id: `0`. Missing field `._vectors.manual.regenerate`\n  - note: `._vectors.manual` must be an array of floats, an array of arrays of floats, or an object with field `regenerate`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -311,7 +311,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Could not parse `._vectors.manual.regenerate`: invalid type: string \"yes please\", expected a boolean at line 1 column 26",
+        "message": "Bad embedder configuration in the document with id: `0`. Could not parse `._vectors.manual.regenerate`: invalid type: string \"yes please\", expected a boolean at line 1 column 26",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -340,7 +340,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings`: expected null or an array, but found a boolean: `true`",
+        "message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings`: expected null or an array, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -369,7 +369,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0]`: expected a number or an array, but found a boolean: `true`",
+        "message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0]`: expected a number or an array, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -398,7 +398,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0][0]`: expected a number, but found a boolean: `true`",
+        "message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0][0]`: expected a number, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -440,7 +440,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[1]`: expected a number, but found an array: `[0.2,0.3]`",
+        "message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[1]`: expected a number, but found an array: `[0.2,0.3]`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -469,7 +469,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[1]`: expected an array, but found a number: `0.3`",
+        "message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[1]`: expected an array, but found a number: `0.3`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -498,7 +498,7 @@ async fn user_provided_embeddings_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0][1]`: expected a number, but found a boolean: `true`",
+        "message": "Bad embedder configuration in the document with id: `0`. Invalid value type at `._vectors.manual.embeddings[0][1]`: expected a number, but found a boolean: `true`",
         "code": "invalid_vectors_type",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_vectors_type"
@@ -539,7 +539,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document `40` and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
+        "message": "While embedding documents for embedder `manual`: no vectors provided for document `40` and at least 4 other document(s)\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: opt-out for a document with `_vectors.manual: null`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -569,7 +569,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document `42`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
+        "message": "While embedding documents for embedder `manual`: no vectors provided for document `42`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vector` by `_vectors` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -599,7 +599,7 @@ async fn user_provided_vectors_error() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `manual`: no vectors provided for document `42`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
+        "message": "While embedding documents for embedder `manual`: no vectors provided for document `42`\n- Note: `manual` has `source: userProvided`, so documents must provide embeddings as an array in `_vectors.manual`.\n- Hint: try replacing `_vectors.manaul` by `_vectors.manual` in 1 document(s).",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"

crates/meilisearch/tests/vector/openai.rs

@@ -713,7 +713,7 @@ async fn bad_api_key() {
         }
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"Incorrect API key provided: Bearer doggo. You can find your API key at https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":\"invalid_api_key\"}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
+        "message": "While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"Incorrect API key provided: Bearer doggo. You can find your API key at https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":\"invalid_api_key\"}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -757,7 +757,7 @@ async fn bad_api_key() {
         }
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accessing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":null}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
+        "message": "While embedding documents for embedder `default`: user error: could not authenticate against OpenAI server\n  - server replied with `{\"error\":{\"message\":\"You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY), or as the password field (with blank username) if you're accessing the API from your browser and are prompted for a username and password. You can obtain an API key from https://platform.openai.com/account/api-keys.\",\"type\":\"invalid_request_error\",\"param\":null,\"code\":null}}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration, and the `MEILI_OPENAI_API_KEY` and `OPENAI_API_KEY` environment variables",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"

crates/meilisearch/tests/vector/rest.rs

@@ -985,7 +985,7 @@ async fn bad_settings() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting a single \"{{embedding}}\", expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting a single \"{{embedding}}\", expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1025,7 +1025,7 @@ async fn bad_settings() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `rest`: runtime error: was expecting embeddings of dimension `2`, got embeddings of dimensions `3`",
+        "message": "While embedding documents for embedder `rest`: runtime error: was expecting embeddings of dimension `2`, got embeddings of dimensions `3`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1178,7 +1178,7 @@ async fn server_returns_bad_request() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"test\\\", expected struct MultipleRequest at line 1 column 6\"}`",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"test\\\", expected struct MultipleRequest at line 1 column 6\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1247,7 +1247,7 @@ async fn server_returns_bad_request() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `rest`: user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"name: kefir\\\\n\\\", expected struct MultipleRequest at line 1 column 15\"}`",
+        "message": "While embedding documents for embedder `rest`: user error: sent a bad request to embedding server\n  - Hint: check that the `request` in the embedder configuration matches the remote server's API\n  - server replied with `{\"error\":\"Invalid request: invalid type: string \\\"name: kefir\\\\n\\\", expected struct MultipleRequest at line 1 column 15\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1306,7 +1306,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting the array of \"{{embedding}}\"s, configuration expects `response` to be an array with at least 1 item(s) but server sent an object with 1 field(s)",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting the array of \"{{embedding}}\"s, configuration expects `response` to be an array with at least 1 item(s) but server sent an object with 1 field(s)",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1362,7 +1362,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting item #0 from the array of \"{{embedding}}\"s, expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response`, while extracting item #0 from the array of \"{{embedding}}\"s, expected `response` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected a sequence",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1414,7 +1414,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output`, while extracting a single \"{{embedding}}\", expected `output` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected f32",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output`, while extracting a single \"{{embedding}}\", expected `output` to be an array of numbers, but failed to parse server response:\n  - invalid type: map, expected f32",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1478,7 +1478,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.embedding`, while extracting item #0 from the array of \"{{embedding}}\"s, configuration expects `embedding` to be an object with key `data` but server sent an array of size 3",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.embedding`, while extracting item #0 from the array of \"{{embedding}}\"s, configuration expects `embedding` to be an object with key `data` but server sent an array of size 3",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1542,7 +1542,7 @@ async fn server_returns_bad_response() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output[0]`, while extracting a single \"{{embedding}}\", configuration expects key \"embeddings\", which is missing in response\n  - Hint: item #0 inside `output` has key `embedding`, did you mean `response.output[0].embedding` in embedder configuration?",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with runtime error: error extracting embeddings from the response:\n  - in `response.output[0]`, while extracting a single \"{{embedding}}\", configuration expects key \"embeddings\", which is missing in response\n  - Hint: item #0 inside `output` has key `embedding`, did you mean `response.output[0].embedding` in embedder configuration?",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1908,7 +1908,7 @@ async fn server_custom_header() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"missing header 'my-nonstandard-auth'\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -1951,7 +1951,7 @@ async fn server_custom_header() {
         }
       },
       "error": {
-        "message": "Index `doggo`: Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
+        "message": "Error while generating embeddings: runtime error: could not determine model dimensions:\n  - test embedding failed with user error: could not authenticate against embedding server\n  - server replied with `{\"error\":\"thou shall not pass, Balrog\"}`\n  - Hint: Check the `apiKey` parameter in the embedder configuration",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"
@@ -2099,7 +2099,7 @@ async fn searchable_reindex() {
         ]
       },
       "error": {
-        "message": "Index `doggo`: While embedding documents for embedder `rest`: error: received unexpected HTTP 404 from embedding server\n  - server replied with `{\"error\":\"text not found\",\"text\":\"breed: patou\\n\"}`",
+        "message": "While embedding documents for embedder `rest`: error: received unexpected HTTP 404 from embedding server\n  - server replied with `{\"error\":\"text not found\",\"text\":\"breed: patou\\n\"}`",
         "code": "vector_embedding_error",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#vector_embedding_error"

crates/milli/src/update/new/channel.rs

@@ -21,15 +21,11 @@ use super::ref_cell_ext::RefCellExt;
 use super::thread_local::{FullySend, ThreadLocal};
 use super::StdResult;
 use crate::heed_codec::facet::{FieldDocIdFacetF64Codec, FieldDocIdFacetStringCodec};
-use crate::heed_codec::StrBEU16Codec;
 use crate::index::db_name;
 use crate::index::main_key::{GEO_FACETED_DOCUMENTS_IDS_KEY, GEO_RTREE_KEY};
 use crate::update::new::KvReaderFieldId;
 use crate::vector::Embedding;
-use crate::{
-    CboRoaringBitmapCodec, DocumentId, Error, FieldIdWordCountCodec, Index, InternalError,
-    U8StrStrCodec,
-};
+use crate::{CboRoaringBitmapCodec, DocumentId, Error, Index, InternalError};
 
 /// Creates a tuple of senders/receiver to be used by
 /// the extractors and the writer loop.
@@ -407,32 +403,6 @@ impl Database {
             Database::FieldIdDocidFacetF64s => db_name::FIELD_ID_DOCID_FACET_F64S,
         }
     }
-
-    pub fn stringify_key(&self, key: &[u8]) -> String {
-        use heed::types::*;
-
-        match self {
-            Database::WordDocids => format!("{:?}", Str::bytes_decode(key).unwrap()),
-            Database::WordFidDocids => format!("{:?}", StrBEU16Codec::bytes_decode(key).unwrap()),
-            Database::WordPositionDocids => {
-                format!("{:?}", StrBEU16Codec::bytes_decode(key).unwrap())
-            }
-            Database::WordPairProximityDocids => {
-                format!("{:?}", U8StrStrCodec::bytes_decode(key).unwrap())
-            }
-            Database::ExactWordDocids => format!("{:?}", Str::bytes_decode(key).unwrap()),
-            Database::FidWordCountDocids => {
-                format!("{:?}", FieldIdWordCountCodec::bytes_decode(key).unwrap())
-            }
-            Database::FieldIdDocidFacetStrings => {
-                format!("{:?}", FieldDocIdFacetStringCodec::bytes_decode(key).unwrap())
-            }
-            Database::FieldIdDocidFacetF64s => {
-                format!("{:?}", FieldDocIdFacetF64Codec::bytes_decode(key).unwrap())
-            }
-            d => unimplemented!("stringify_key for {:?}", d),
-        }
-    }
 }
 
 impl From<FacetKind> for Database {

crates/milli/src/update/new/document.rs

@@ -1,5 +1,6 @@
 use std::collections::{BTreeMap, BTreeSet};
 
+use either::Either;
 use heed::RoTxn;
 use raw_collections::RawMap;
 use serde_json::value::RawValue;
@@ -209,11 +210,13 @@ impl<'d, 'doc: 'd, 't: 'd, Mapper: FieldIdMapper> Document<'d>
     for MergedDocument<'d, 'doc, 't, Mapper>
 {
     fn iter_top_level_fields(&self) -> impl Iterator<Item = Result<(&'d str, &'d RawValue)>> {
+        match &self.db {
+            Some(db) => {
                 let mut new_doc_it = self.new_doc.iter_top_level_fields();
-        let mut db_it = self.db.iter().flat_map(|db| db.iter_top_level_fields());
+                let mut db_it = db.iter_top_level_fields();
                 let mut seen_fields = BTreeSet::new();
 
-        std::iter::from_fn(move || {
+                Either::Left(std::iter::from_fn(move || {
                     if let Some(next) = new_doc_it.next() {
                         if let Ok((name, _)) = next {
                             seen_fields.insert(name);
@@ -231,7 +234,10 @@ impl<'d, 'doc: 'd, 't: 'd, Mapper: FieldIdMapper> Document<'d>
                             Err(err) => return Some(Err(err)),
                         }
                     }
-        })
+                }))
+            }
+            None => Either::Right(self.new_doc.iter_top_level_fields()),
+        }
     }
 
     fn vectors_field(&self) -> Result<Option<&'d RawValue>> {

crates/milli/src/update/new/extract/searchable/extract_word_docids.rs

@@ -28,7 +28,7 @@ pub struct WordDocidsBalancedCaches<'extractor> {
     exact_word_docids: BalancedCaches<'extractor>,
     word_position_docids: BalancedCaches<'extractor>,
     fid_word_count_docids: BalancedCaches<'extractor>,
-    fid_word_count: HashMap<FieldId, (Option<usize>, Option<usize>)>,
+    fid_word_count: HashMap<FieldId, (usize, usize)>,
     current_docid: Option<DocumentId>,
 }
 
@@ -85,8 +85,8 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
 
         self.fid_word_count
             .entry(field_id)
-            .and_modify(|(_current_count, new_count)| *new_count.get_or_insert(0) += 1)
-            .or_insert((None, Some(1)));
+            .and_modify(|(_current_count, new_count)| *new_count += 1)
+            .or_insert((0, 1));
         self.current_docid = Some(docid);
 
         Ok(())
@@ -130,8 +130,8 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
 
         self.fid_word_count
             .entry(field_id)
-            .and_modify(|(current_count, _new_count)| *current_count.get_or_insert(0) += 1)
-            .or_insert((Some(1), None));
+            .and_modify(|(current_count, _new_count)| *current_count += 1)
+            .or_insert((1, 0));
 
         self.current_docid = Some(docid);
 
@@ -141,18 +141,14 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
     fn flush_fid_word_count(&mut self, buffer: &mut BumpVec<u8>) -> Result<()> {
         for (fid, (current_count, new_count)) in self.fid_word_count.drain() {
             if current_count != new_count {
-                if let Some(current_count) =
-                    current_count.filter(|current_count| *current_count <= MAX_COUNTED_WORDS)
-                {
+                if current_count <= MAX_COUNTED_WORDS {
                     buffer.clear();
                     buffer.extend_from_slice(&fid.to_be_bytes());
                     buffer.push(current_count as u8);
                     self.fid_word_count_docids
                         .insert_del_u32(buffer, self.current_docid.unwrap())?;
                 }
-                if let Some(new_count) =
-                    new_count.filter(|new_count| *new_count <= MAX_COUNTED_WORDS)
-                {
+                if new_count <= MAX_COUNTED_WORDS {
                     buffer.clear();
                     buffer.extend_from_slice(&fid.to_be_bytes());
                     buffer.push(new_count as u8);

crates/milli/src/update/new/indexer/mod.rs

@@ -80,15 +80,6 @@ where
     let mut bbbuffers = Vec::new();
     let finished_extraction = AtomicBool::new(false);
 
-    // We reduce the actual memory used to 5%. The reason we do this here and not in Meilisearch
-    // is because we still use the old indexer for the settings and it is highly impacted by the
-    // max memory. So we keep the changes here and will remove these changes once we use the new
-    // indexer to also index settings. Related to #5125 and #5141.
-    let grenad_parameters = GrenadParameters {
-        max_memory: grenad_parameters.max_memory.map(|mm| mm * 5 / 100),
-        ..grenad_parameters
-    };
-
     // We compute and remove the allocated BBQueues buffers capacity from the indexing memory.
     let minimum_capacity = 50 * 1024 * 1024 * pool.current_num_threads(); // 50 MiB
     let (grenad_parameters, total_bbbuffer_capacity) = grenad_parameters.max_memory.map_or(

crates/milli/src/update/new/merger.rs

@@ -80,35 +80,16 @@ where
         }
         merge_caches_sorted(frozen, |key, DelAddRoaringBitmap { del, add }| {
             let current = database.get(&rtxn, key)?;
-
-            if let (Some(del), Some(current)) = (&del, &current) {
-                let current = CboRoaringBitmapCodec::deserialize_from(current).unwrap();
-                let diff = del - &current;
-                let external_ids = index.external_id_of(&rtxn, &diff).unwrap().into_iter().map(|id| id.unwrap()).collect::<Vec<_>>();
-                if !del.is_subset(&current) {
-                    eprintln!(
-                        "======================== {:?}: {} ->  c: {:?} d: {:?} a: {:?} extra: {:?} extra_external_ids: {:?}",
-                        D::DATABASE,
-                        D::DATABASE.stringify_key(key),
-                        &current,
-                        del,
-                        add,
-                        diff,
-                        external_ids
-                    );
-                }
-            }
-            match merge_cbo_bitmaps(current, del, add) {
-                Ok(Operation::Write(bitmap)) => {
+            match merge_cbo_bitmaps(current, del, add)? {
+                Operation::Write(bitmap) => {
                     docids_sender.write(key, &bitmap)?;
                     Ok(())
                 }
-                Ok(Operation::Delete) => {
+                Operation::Delete => {
                     docids_sender.delete(key)?;
                     Ok(())
                 }
-                Ok(Operation::Ignore) => Ok(()),
-                Err(e) => Err(e),
+                Operation::Ignore => Ok(()),
             }
         })
     })
@@ -253,47 +234,18 @@ fn merge_cbo_bitmaps(
         (None, Some(_del), Some(add)) => Ok(Operation::Write(add)),
         (Some(_current), None, None) => Ok(Operation::Ignore), // but it's strange
         (Some(current), None, Some(add)) => Ok(Operation::Write(current | add)),
-        (Some(current), Some(mut del), add) => {
-            debug_assert!(
-                del.is_subset(&current),
-                "del is not a subset of current, which must be impossible."
-            );
+        (Some(current), Some(del), add) => {
             let output = match add {
-                Some(add) => {
-                    del -= &add;
-
-                    if del.is_empty() {
-                        if add.is_subset(&current) {
-                            // no changes, no allocation
-                            None
-                        } else {
-                            // addition
-                            Some(current | add)
-                        }
-                    } else {
-                        if add.is_subset(&current) {
-                            // deletion only, no union
-                            Some(current - del)
-                        } else {
-                            // deletion and addition
-                            Some((current - del) | add)
-                        }
-                    }
-                }
-                // deletion only, no union
-                None => Some(current - del),
+                Some(add) => (&current - del) | add,
+                None => &current - del,
             };
-
-            match output {
-                Some(output) => {
             if output.is_empty() {
                 Ok(Operation::Delete)
+            } else if current == output {
+                Ok(Operation::Ignore)
             } else {
                 Ok(Operation::Write(output))
             }
         }
-                None => Ok(Operation::Ignore),
-            }
-        }
     }
 }

crates/xtask/src/bench/mod.rs

@@ -139,7 +139,7 @@ pub fn run(args: BenchDeriveArgs) -> anyhow::Result<()> {
     rt.block_on(async {
         dashboard_client.send_machine_info(&env).await?;
 
-        let commit_message = build_info.commit_msg.unwrap_or_default().split('\n').next().unwrap();
+        let commit_message = build_info.commit_msg.context("missing commit message")?.split('\n').next().unwrap();
         let max_workloads = args.workload_file.len();
         let reason: Option<&str> = args.reason.as_deref();
         let invocation_uuid = dashboard_client.create_invocation(build_info.clone(), commit_message, env, max_workloads, reason).await?;